Methods › Computer Vision › Output Heads › Dynamic Keypoint Head
Dynamic Keypoint Head
Introduced by Weian Mao et al. in FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Dynamic Keypoint Head is an output head for pose estimation that are conditioned on each instance (person), and can encode the instance concept in the dynamically-generated weights of their filters. They are used in the FCPose architecture.
The Figure shows the core idea. F denotes a level of feature maps. "Rel. Coord." means the relative coordinates, denoting the relative offsets from the locations of F to the location where the filters are generated. Refer to the text for details. f_(θᵢ) is the dynamically-generated keypoint head for the i-th person instance. Note that each person instance has its own keypoint head.
Papers archive 2025-07-28
1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions 29 May 2021 · 3 repositories · arXiv:2105.14185
Tasks archive 2025-07-28
3 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Keypoint Estimation | 1 |
| Multi-Person Pose Estimation | 1 |
| Pose Estimation | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections